AMD Ryzen Threadripper 3990X 64-Core benchmarks for a future article by Michael Larabel.
sched-core Git Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 21.10, Kernel: 5.17.0-rc1-sched-core-phx (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server, OpenGL: 4.6 Mesa 21.2.2 (LLVM 12.0.1), Vulkan: 1.2.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039Python Notes: Python 3.9.7Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Linux 5.17 Git OS: Pop 21.10, Kernel: 5.17.0-051700rc6daily20220301-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server, OpenGL: 4.6 Mesa 21.2.2 (LLVM 12.0.1), Vulkan: 1.2.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
Threadripper 3990X sched-core OpenBenchmarking.org Phoronix Test Suite AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads) Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS) AMD Starship/Matisse 128GB Samsung SSD 970 EVO Plus 500GB AMD Radeon RX 5700 8GB (1750/875MHz) AMD Navi 10 HDMI Audio DELL P2415Q Intel I211 + Intel Wi-Fi 6 AX200 Pop 21.10 5.17.0-rc1-sched-core-phx (x86_64) 5.17.0-051700rc6daily20220301-generic (x86_64) GNOME Shell 40.5 X Server 4.6 Mesa 21.2.2 (LLVM 12.0.1) 1.2.182 GCC 11.2.0 ext4 3840x2160 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernels Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution Threadripper 3990X Sched-core Benchmarks System Logs - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039 - Python 3.9.7 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
sched-core Git vs. Linux 5.17 Git Comparison Phoronix Test Suite Baseline +26.9% +26.9% +53.8% +53.8% +80.7% +80.7% 8.9% 6.2% 5.8% 5.7% 4% 4% 3.8% 3.4% 3.4% 3.2% 3.1% 2.9% 2.8% 2.7% 2.6% 2.1% 32 107.4% 16 99.5% 8 93.7% 64 27.2% 100 - 250 - Read Write 19.8% 100 - 250 - Read Write - Average Latency 19.5% fcn-resnet101-11 - CPU tConvolve OpenMP - Gridding 100 - 100 - Read Write - Average Latency 6% Rotate R.C.a.P - CPU 100 - 100 - Read Write 5.6% tConvolve MPI - Gridding 4.5% tConvolve MPI - Degridding 4.4% OpenMP - Points2Image 4.3% tConvolve OpenMP - Degridding 4% OpenMP - NDT Mapping Speed 9 Realtime - Bosphorus 4K Resizing 100 - 250 - Read Only - Average Latency 100 - 250 - Read Only 100 - 50 - Read Write 3.3% 100 - 50 - Read Write - Average Latency 3.3% leblancbig sedovbig Speed 8 Realtime - Bosphorus 4K Speed 10 Realtime - Bosphorus 4K 26 2.8% Danish Mood - CPU 2.8% 26 2.7% 26 2.7% Swirl S.F.P.R 100 - 50 - Read Only - Average Latency 2.1% 26 2.1% 19 - Compression Speed MariaDB MariaDB MariaDB MariaDB PostgreSQL pgbench PostgreSQL pgbench ONNX Runtime ASKAP PostgreSQL pgbench GraphicsMagick LuxCoreRender PostgreSQL pgbench ASKAP ASKAP Darmstadt Automotive Parallel Heterogeneous Suite ASKAP Darmstadt Automotive Parallel Heterogeneous Suite AOM AV1 GraphicsMagick PostgreSQL pgbench PostgreSQL pgbench PostgreSQL pgbench PostgreSQL pgbench Pennant Pennant AOM AV1 AOM AV1 Graph500 LuxCoreRender Graph500 Graph500 GraphicsMagick ACES DGEMM PostgreSQL pgbench Graph500 Zstd Compression sched-core Git Linux 5.17 Git
Threadripper 3990X sched-core clomp: Static OMP Speedup pennant: sedovbig pennant: leblancbig mrbayes: Primate Phylogeny Analysis qe: AUSURF112 libgav1: Summer Nature 4K libgav1: Summer Nature 1080p libgav1: Chimera 1080p 10-bit compress-zstd: 8 - Compression Speed compress-zstd: 8 - Decompression Speed compress-zstd: 19 - Compression Speed compress-zstd: 19 - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 19, Long Mode - Decompression Speed luxcorerender: DLSC - CPU luxcorerender: Danish Mood - CPU luxcorerender: Orange Juice - CPU luxcorerender: Rainbow Colors and Prism - CPU graphics-magick: Swirl graphics-magick: Rotate graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Resizing graphics-magick: Noise-Gaussian graphics-magick: HWB Color Space dav1d: Summer Nature 4K dav1d: Summer Nature 1080p dav1d: Chimera 1080p 10-bit aom-av1: Speed 6 Realtime - Bosphorus 4K aom-av1: Speed 6 Two-Pass - Bosphorus 4K aom-av1: Speed 8 Realtime - Bosphorus 4K aom-av1: Speed 9 Realtime - Bosphorus 4K aom-av1: Speed 10 Realtime - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 10 - Bosphorus 4K svt-av1: Preset 12 - Bosphorus 4K mt-dgemm: Sustained Floating-Point Rate compress-7zip: Compression Rating compress-7zip: Decompression Rating build-gdb: Time To Compile build-gem5: Time To Compile build-godot: Time To Compile build-linux-kernel: defconfig build-linux-kernel: allmodconfig primesieve: 1e12 Prime Number Generation liquid-dsp: 16 - 256 - 57 liquid-dsp: 32 - 256 - 57 liquid-dsp: 64 - 256 - 57 liquid-dsp: 128 - 256 - 57 askap: tConvolve MT - Gridding askap: tConvolve MT - Degridding askap: tConvolve MPI - Degridding askap: tConvolve MPI - Gridding askap: tConvolve OpenMP - Gridding askap: tConvolve OpenMP - Degridding askap: Hogbom Clean OpenMP graph500: 26 graph500: 26 graph500: 26 graph500: 26 daphne: OpenMP - NDT Mapping daphne: OpenMP - Points2Image daphne: OpenMP - Euclidean Cluster tensorflow-lite: SqueezeNet tensorflow-lite: Inception V4 tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception ResNet V2 mysqlslap: 8 mysqlslap: 16 mysqlslap: 32 mysqlslap: 64 mysqlslap: 128 pgbench: 100 - 50 - Read Only pgbench: 100 - 50 - Read Only - Average Latency pgbench: 100 - 100 - Read Only pgbench: 100 - 100 - Read Only - Average Latency pgbench: 100 - 250 - Read Only pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 50 - Read Write pgbench: 100 - 50 - Read Write - Average Latency pgbench: 100 - 100 - Read Write pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 250 - Read Write pgbench: 100 - 250 - Read Write - Average Latency gpaw: Carbon Nanotube blender: BMW27 - CPU-Only blender: Barbershop - CPU-Only rocksdb: Rand Fill rocksdb: Rand Read rocksdb: Update Rand rocksdb: Read While Writing rocksdb: Read Rand Write Rand onnx: yolov4 - CPU onnx: fcn-resnet101-11 - CPU onnx: shufflenet-v2-10 - CPU onnx: super-resolution-10 - CPU sched-core Git Linux 5.17 Git 55.4 12.45384 5.471451 142.889 391.93 43.49 132.14 40.92 3638.1 3799.6 80.4 3369.4 44.3 3392.6 8.26 6.32 12.70 27.82 2100 619 671 1008 1035 705 1346 386.36 965.12 718.74 9.03 10.31 33.52 44.95 47.92 89.081 140.692 163.964 16.692992 196330 360623 42.186 194.188 49.434 25.376 252.782 3.983 962743333 1777633333 2822833333 3040233333 2146.42 3183.93 18362.2 16748.9 5831.05 4034.18 361.450 543456000 549848000 164643000 216593000 982.56 17081.147186083 1139.51 48519.5 623517 74045.3 28423.1 29578.7 568372 955 878 757 369 230 1068251 0.047 1347286 0.074 1638373 0.153 5861 8.542 7779 12.886 9116 27.539 106.720 28.88 304.22 366831 245874918 350863 9336682 2885383 292 157 11067 7597 55.3 12.08188 5.300170 141.704 390.93 44.13 134.19 41.08 3652.4 3809.7 82.1 3355.8 44.2 3365.6 8.24 6.15 12.59 29.41 2156 655 674 1014 1074 717 1365 388.26 964.33 717.75 9.19 10.26 34.49 46.74 49.28 89.737 140.044 165.717 17.129724 196124 363282 42.494 191.386 49.654 25.457 253.699 3.956 972203333 1786266667 2836166667 3036233333 2145.87 3182.74 17596.0 16031.5 6192 3877.70 361.447 529167000 538402000 160144000 210867000 1021.96 16384.655792573 1141.46 48235.5 627090 74051.7 28500.3 29607.6 564887 493 440 365 290 232 1053840 0.048 1324265 0.075 1693607 0.148 5673 8.824 7363 13.653 7612 32.897 106.930 28.56 303.91 364172 250588886 349595 9404219 2898792 294 171 10962 7570 OpenBenchmarking.org
CLOMP CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup Linux 5.17 Git sched-core Git 12 24 36 48 60 SE +/- 0.70, N = 3 SE +/- 0.52, N = 3 55.3 55.4 1. (CC) gcc options: -fopenmp -O3 -lm
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig Linux 5.17 Git sched-core Git 1.2311 2.4622 3.6933 4.9244 6.1555 SE +/- 0.050854, N = 3 SE +/- 0.053394, N = 15 5.300170 5.471451 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
Timed MrBayes Analysis This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Linux 5.17 Git sched-core Git 30 60 90 120 150 SE +/- 1.77, N = 3 SE +/- 1.07, N = 3 141.70 142.89 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
Quantum ESPRESSO Quantum ESPRESSO is an integrated suite of Open-Source computer codes for electronic-structure calculations and materials modeling at the nanoscale. It is based on density-functional theory, plane waves, and pseudopotentials. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 7.0 Input: AUSURF112 Linux 5.17 Git sched-core Git 90 180 270 360 450 SE +/- 1.11, N = 3 SE +/- 2.53, N = 3 390.93 391.93 1. (F9X) gfortran options: -pthread -fopenmp -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3_omp -lfftw3 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Summer Nature 1080p Linux 5.17 Git sched-core Git 30 60 90 120 150 SE +/- 0.22, N = 3 SE +/- 0.33, N = 3 134.19 132.14 1. (CXX) g++ options: -O3 -lrt
OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Chimera 1080p 10-bit Linux 5.17 Git sched-core Git 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 41.08 40.92 1. (CXX) g++ options: -O3 -lrt
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed Linux 5.17 Git sched-core Git 800 1600 2400 3200 4000 SE +/- 37.56, N = 4 SE +/- 19.62, N = 3 3652.4 3638.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed Linux 5.17 Git sched-core Git 800 1600 2400 3200 4000 SE +/- 9.40, N = 4 SE +/- 9.46, N = 3 3809.7 3799.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Linux 5.17 Git sched-core Git 20 40 60 80 100 SE +/- 0.54, N = 15 SE +/- 0.73, N = 3 82.1 80.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed Linux 5.17 Git sched-core Git 700 1400 2100 2800 3500 SE +/- 4.49, N = 15 SE +/- 14.49, N = 3 3355.8 3369.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed Linux 5.17 Git sched-core Git 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 44.2 44.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed Linux 5.17 Git sched-core Git 700 1400 2100 2800 3500 SE +/- 5.28, N = 3 SE +/- 9.15, N = 3 3365.6 3392.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU Linux 5.17 Git sched-core Git 2 4 6 8 10 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 8.24 8.26 MIN: 7.96 / MAX: 9.08 MIN: 8.09 / MAX: 8.98
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: CPU Linux 5.17 Git sched-core Git 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.07, N = 5 6.15 6.32 MIN: 2.51 / MAX: 7.23 MIN: 2.59 / MAX: 7.54
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU Linux 5.17 Git sched-core Git 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.12, N = 6 12.59 12.70 MIN: 10.73 / MAX: 14.54 MIN: 10.69 / MAX: 15.2
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: CPU Linux 5.17 Git sched-core Git 7 14 21 28 35 SE +/- 0.29, N = 3 SE +/- 0.34, N = 3 29.41 27.82 MIN: 28.59 / MAX: 30.36 MIN: 24.19 / MAX: 28.68
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Linux 5.17 Git sched-core Git 500 1000 1500 2000 2500 SE +/- 7.36, N = 3 SE +/- 10.97, N = 3 2156 2100 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Linux 5.17 Git sched-core Git 140 280 420 560 700 SE +/- 1.73, N = 3 SE +/- 1.86, N = 3 655 619 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen Linux 5.17 Git sched-core Git 150 300 450 600 750 SE +/- 4.16, N = 3 SE +/- 4.04, N = 3 674 671 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 4.93, N = 3 SE +/- 4.70, N = 3 1014 1008 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 19.31, N = 15 SE +/- 14.80, N = 15 1074 1035 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Linux 5.17 Git sched-core Git 150 300 450 600 750 SE +/- 1.45, N = 3 SE +/- 0.33, N = 3 717 705 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Linux 5.17 Git sched-core Git 300 600 900 1200 1500 SE +/- 3.06, N = 3 SE +/- 6.17, N = 3 1365 1346 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 4K Linux 5.17 Git sched-core Git 80 160 240 320 400 SE +/- 0.85, N = 3 SE +/- 1.22, N = 3 388.26 386.36 MIN: 192.76 / MAX: 414.49 MIN: 186.53 / MAX: 414.14 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 1080p Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 0.74, N = 3 SE +/- 6.97, N = 3 964.33 965.12 MIN: 439 / MAX: 1069.47 MIN: 411.89 / MAX: 1082.48 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Chimera 1080p 10-bit Linux 5.17 Git sched-core Git 160 320 480 640 800 SE +/- 0.76, N = 3 SE +/- 1.64, N = 3 717.75 718.74 MIN: 460.19 / MAX: 898.59 MIN: 461.45 / MAX: 897.2 1. (CC) gcc options: -pthread -lm
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Linux 5.17 Git sched-core Git 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 9.19 9.03 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Linux 5.17 Git sched-core Git 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 10.26 10.31 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Linux 5.17 Git sched-core Git 8 16 24 32 40 SE +/- 0.26, N = 3 SE +/- 0.30, N = 3 34.49 33.52 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Linux 5.17 Git sched-core Git 11 22 33 44 55 SE +/- 0.40, N = 3 SE +/- 0.33, N = 3 46.74 44.95 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Linux 5.17 Git sched-core Git 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.47, N = 3 49.28 47.92 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 8 - Input: Bosphorus 4K Linux 5.17 Git sched-core Git 20 40 60 80 100 SE +/- 0.98, N = 3 SE +/- 0.56, N = 3 89.74 89.08 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 10 - Input: Bosphorus 4K Linux 5.17 Git sched-core Git 30 60 90 120 150 SE +/- 0.70, N = 3 SE +/- 1.03, N = 3 140.04 140.69 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 12 - Input: Bosphorus 4K Linux 5.17 Git sched-core Git 40 80 120 160 200 SE +/- 0.46, N = 3 SE +/- 0.18, N = 3 165.72 163.96 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Decompression Rating Linux 5.17 Git sched-core Git 80K 160K 240K 320K 400K SE +/- 2278.14, N = 3 SE +/- 2391.99, N = 3 363282 360623 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Primesieve Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.7 1e12 Prime Number Generation Linux 5.17 Git sched-core Git 0.8962 1.7924 2.6886 3.5848 4.481 SE +/- 0.007, N = 3 SE +/- 0.012, N = 3 3.956 3.983 1. (CXX) g++ options: -O3
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 16 - Buffer Length: 256 - Filter Length: 57 Linux 5.17 Git sched-core Git 200M 400M 600M 800M 1000M SE +/- 2670919.53, N = 3 SE +/- 4496355.31, N = 3 972203333 962743333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 Linux 5.17 Git sched-core Git 400M 800M 1200M 1600M 2000M SE +/- 6854763.15, N = 3 SE +/- 5607534.61, N = 3 1786266667 1777633333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Linux 5.17 Git sched-core Git 600M 1200M 1800M 2400M 3000M SE +/- 5117399.51, N = 3 SE +/- 1927289.40, N = 3 2836166667 2822833333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Linux 5.17 Git sched-core Git 700M 1400M 2100M 2800M 3500M SE +/- 16229226.04, N = 3 SE +/- 8936131.40, N = 3 3036233333 3040233333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding Linux 5.17 Git sched-core Git 500 1000 1500 2000 2500 SE +/- 0.74, N = 3 SE +/- 0.95, N = 3 2145.87 2146.42 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding Linux 5.17 Git sched-core Git 700 1400 2100 2800 3500 SE +/- 0.79, N = 3 SE +/- 1.07, N = 3 3182.74 3183.93 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding Linux 5.17 Git sched-core Git 4K 8K 12K 16K 20K SE +/- 213.40, N = 3 SE +/- 141.05, N = 3 17596.0 18362.2 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding Linux 5.17 Git sched-core Git 4K 8K 12K 16K 20K SE +/- 241.07, N = 3 SE +/- 44.43, N = 3 16031.5 16748.9 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding Linux 5.17 Git sched-core Git 1300 2600 3900 5200 6500 SE +/- 0.00, N = 3 SE +/- 42.88, N = 3 6192.00 5831.05 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding Linux 5.17 Git sched-core Git 900 1800 2700 3600 4500 SE +/- 18.92, N = 3 SE +/- 0.00, N = 3 3877.70 4034.18 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Iterations Per Second, More Is Better ASKAP 1.0 Test: Hogbom Clean OpenMP Linux 5.17 Git sched-core Git 80 160 240 320 400 SE +/- 0.44, N = 3 SE +/- 0.87, N = 3 361.45 361.45 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Graph500 OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 Linux 5.17 Git sched-core Git 120M 240M 360M 480M 600M 529167000 543456000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 Linux 5.17 Git sched-core Git 120M 240M 360M 480M 600M 538402000 549848000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 Linux 5.17 Git sched-core Git 40M 80M 120M 160M 200M 160144000 164643000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org sssp max_TEPS, More Is Better Graph500 3.0 Scale: 26 Linux 5.17 Git sched-core Git 50M 100M 150M 200M 250M 210867000 216593000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
Darmstadt Automotive Parallel Heterogeneous Suite DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: NDT Mapping Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 2.55, N = 3 SE +/- 7.91, N = 3 1021.96 982.56 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 16 Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 22.18, N = 9 SE +/- 2.19, N = 3 440 878 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 32 Linux 5.17 Git sched-core Git 160 320 480 640 800 SE +/- 13.41, N = 6 SE +/- 0.83, N = 3 365 757 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 64 Linux 5.17 Git sched-core Git 80 160 240 320 400 SE +/- 6.49, N = 6 SE +/- 43.05, N = 6 290 369 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 128 Linux 5.17 Git sched-core Git 50 100 150 200 250 SE +/- 2.49, N = 3 SE +/- 1.81, N = 3 232 230 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency Linux 5.17 Git sched-core Git 0.0108 0.0216 0.0324 0.0432 0.054 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.048 0.047 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only Linux 5.17 Git sched-core Git 300K 600K 900K 1200K 1500K SE +/- 3253.09, N = 3 SE +/- 3473.78, N = 3 1324265 1347286 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency Linux 5.17 Git sched-core Git 0.0169 0.0338 0.0507 0.0676 0.0845 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.075 0.074 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only Linux 5.17 Git sched-core Git 400K 800K 1200K 1600K 2000K SE +/- 9806.45, N = 3 SE +/- 13238.24, N = 3 1693607 1638373 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency Linux 5.17 Git sched-core Git 0.0344 0.0688 0.1032 0.1376 0.172 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.148 0.153 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write Linux 5.17 Git sched-core Git 1300 2600 3900 5200 6500 SE +/- 61.29, N = 12 SE +/- 62.50, N = 12 5673 5861 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency Linux 5.17 Git sched-core Git 2 4 6 8 10 SE +/- 0.094, N = 12 SE +/- 0.089, N = 12 8.824 8.542 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write Linux 5.17 Git sched-core Git 2K 4K 6K 8K 10K SE +/- 160.77, N = 12 SE +/- 114.09, N = 12 7363 7779 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency Linux 5.17 Git sched-core Git 4 8 12 16 20 SE +/- 0.30, N = 12 SE +/- 0.19, N = 12 13.65 12.89 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write Linux 5.17 Git sched-core Git 2K 4K 6K 8K 10K SE +/- 93.95, N = 12 SE +/- 175.38, N = 12 7612 9116 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency Linux 5.17 Git sched-core Git 8 16 24 32 40 SE +/- 0.41, N = 12 SE +/- 0.54, N = 12 32.90 27.54 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
GPAW GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GPAW 22.1 Input: Carbon Nanotube Linux 5.17 Git sched-core Git 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 106.93 106.72 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: BMW27 - Compute: CPU-Only Linux 5.17 Git sched-core Git 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.13, N = 3 28.56 28.88
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Barbershop - Compute: CPU-Only Linux 5.17 Git sched-core Git 70 140 210 280 350 SE +/- 1.48, N = 3 SE +/- 0.50, N = 3 303.91 304.22
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Linux 5.17 Git sched-core Git 80K 160K 240K 320K 400K SE +/- 2998.42, N = 3 SE +/- 1716.59, N = 3 364172 366831 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read Linux 5.17 Git sched-core Git 50M 100M 150M 200M 250M SE +/- 2676219.89, N = 5 SE +/- 3795798.11, N = 15 250588886 245874918 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random Linux 5.17 Git sched-core Git 80K 160K 240K 320K 400K SE +/- 173.12, N = 3 SE +/- 129.48, N = 3 349595 350863 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing Linux 5.17 Git sched-core Git 2M 4M 6M 8M 10M SE +/- 11254.13, N = 3 SE +/- 132127.81, N = 3 9404219 9336682 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random Linux 5.17 Git sched-core Git 600K 1200K 1800K 2400K 3000K SE +/- 8841.26, N = 3 SE +/- 18021.62, N = 3 2898792 2885383 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: yolov4 - Device: CPU Linux 5.17 Git sched-core Git 60 120 180 240 300 SE +/- 4.94, N = 12 SE +/- 1.88, N = 3 294 292 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: fcn-resnet101-11 - Device: CPU Linux 5.17 Git sched-core Git 40 80 120 160 200 SE +/- 4.86, N = 12 SE +/- 0.33, N = 3 171 157 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: shufflenet-v2-10 - Device: CPU Linux 5.17 Git sched-core Git 2K 4K 6K 8K 10K SE +/- 23.74, N = 3 SE +/- 21.42, N = 3 10962 11067 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: super-resolution-10 - Device: CPU Linux 5.17 Git sched-core Git 1600 3200 4800 6400 8000 SE +/- 41.64, N = 3 SE +/- 30.29, N = 3 7570 7597 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
sched-core Git Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 21.10, Kernel: 5.17.0-rc1-sched-core-phx (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server, OpenGL: 4.6 Mesa 21.2.2 (LLVM 12.0.1), Vulkan: 1.2.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039Python Notes: Python 3.9.7Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 1 March 2022 05:27 by user pts.
Linux 5.17 Git Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 21.10, Kernel: 5.17.0-051700rc6daily20220301-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server, OpenGL: 4.6 Mesa 21.2.2 (LLVM 12.0.1), Vulkan: 1.2.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039Python Notes: Python 3.9.7Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 1 March 2022 17:52 by user pts.